English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Inferring the probability distribution of sentences or word sequences is akey process in natural language processing. While word-level language models(LMs) have been widely adopted for computing the joint probabilities of wordsequences, they have difficulty in capturing a context long enough for sentenceprobability estimation (SPE). To overcome this, recent studies introducedtraining methods using sentence-level noise-contrastive estimation (NCE) withrecurrent neural networks (RNNs). In this work, we attempt to extend it forcontextual SPE, which aims to estimate a conditional sentence probability givena previous text. The proposed NCE samples negative sentences independently of aprevious text so that the trained model gives higher probabilities to thesentences that are more consistent with \textcolor{blue}{the} context. We applyour method to a simple word-level RNN LM to focus on the effect of thesentence-level NCE training rather than on the network architecture. Thequality of estimation was evaluated against multiple-choice cloze-stylequestions including both human and automatically generated questions. Theexperimental results show that the proposed method improved the SPE quality forthe word-level RNN LM.

Learning a Word-Level Language Model with Sentence-Level Noise Contrastive Estimation for Contextual Sentence Probability Estimation